Conversational Factor Information Retrieval Model (ConFIRM)
This addresses data scarcity for domain-specific AI retrieval systems, though it is incremental as it builds on existing fine-tuning and synthetic data methods.
The paper tackled the problem of data scarcity in domain-specific retrieval tasks by fine-tuning LLMs with personality-aligned synthetic datasets, achieving 91% accuracy in classifying financial queries with an average inference time of 0.61 seconds.
This paper introduces the Conversational Factor Information Retrieval Method (ConFIRM), a novel approach to fine-tuning large language models (LLMs) for domain-specific retrieval tasks. ConFIRM leverages the Five-Factor Model of personality to generate synthetic datasets that accurately reflect target population characteristics, addressing data scarcity in specialized domains. We demonstrate ConFIRM's effectiveness through a case study in the finance sector, fine-tuning a Llama-2-7b model using personality-aligned data from the PolyU-Asklora Fintech Adoption Index. The resulting model achieved 91% accuracy in classifying financial queries, with an average inference time of 0.61 seconds on an NVIDIA A100 GPU. ConFIRM shows promise for creating more accurate and personalized AI-driven information retrieval systems across various domains, potentially mitigating issues of hallucinations and outdated information in LLMs deployed